Speech as a Biomarker for Depression

2021 ◽  
Vol 20 ◽  
Author(s):  
Sanne Koops ◽  
Sanne G. Brederoo ◽  
Janna N. de Boer ◽  
Femke G. Nadema ◽  
Alban E. Voppel ◽  
...  
Keyword(s):  
Computational Modeling ◽  
Ethical Issues ◽  
Speech Rate ◽  
Language Models ◽  
Speech Analysis ◽  
Machine Learning Techniques ◽  
Special Focus ◽  
Data Types ◽  
Wide Range ◽  
Modeling Techniques

Background: Depression is a debilitating disorder that at present lacks a reliable biomarker to aid in diagnosis and early detection. Recent advances in computational analytic approaches have opened up new avenues in developing such a biomarker by taking advantage of the wealth of information that can be extracted from a person’s speech. Objective: The current review provides an overview of the latest findings in the rapidly evolving field of computational language analysis for the detection of depression. We cover a wide range of both acoustic and content-related linguistic features, data types (i.e., spoken and written language), and data sources (i.e., lab settings, social media, and smartphone-based). We put special focus on the current methodological advances with regard to feature extraction and computational modeling techniques. Furthermore, we pay attention to potential hurdles in the implementation of automatic speech analysis. Conclusion: Depressive speech is characterized by several anomalies, such as lower speech rate, less pitch variability and more self-referential speech. With current computational modeling techniques, such features can be used to detect depression with an accuracy of up to 91%. The performance of the models is optimized when machine learning techniques are implemented that suit the type and amount of data. Recent studies now work towards further optimization and generalizability of the computational language models to detect depression. Finally, privacy and ethical issues are of paramount importance to be addressed when automatic speech analysis techniques are further implemented in, for example, smartphones. Altogether, computational speech analysis is well underway towards becoming an effective diagnostic aid for depression.

scholarly journals Computational Modeling Intervertebral Disc Pathophysiology: A Review

2022 ◽  
Vol 12 ◽  
Author(s):  
Mallory Volz ◽  
Shady Elmasry ◽  
Alicia R. Jackson ◽  
Francesco Travascio
Keyword(s):  
Intervertebral Disc ◽  
Computational Modeling ◽  
Medical Condition ◽  
Primary Source ◽  
Special Focus ◽  
Biochemical Alterations ◽  
Wide Range ◽  
Mechanical Factors ◽  
Ivd Degeneration ◽  
Physical Changes

Lower back pain is a medical condition of epidemic proportion, and the degeneration of the intervertebral disc has been identified as a major contributor. The etiology of intervertebral disc (IVD) degeneration is multifactorial, depending on age, cell-mediated molecular degradation processes and genetics, which is accelerated by traumatic or gradual mechanical factors. The complexity of such intertwined biochemical and mechanical processes leading to degeneration makes it difficult to quantitatively identify cause–effect relationships through experiments. Computational modeling of the IVD is a powerful investigative tool since it offers the opportunity to vary, observe and isolate the effects of a wide range of phenomena involved in the degenerative process of discs. This review aims at discussing the main findings of finite element models of IVD pathophysiology with a special focus on the different factors contributing to physical changes typical of degenerative phenomena. Models presented are subdivided into those addressing role of nutritional supply, progressive biochemical alterations stemming from an imbalance between anabolic and catabolic processes, aging and those considering mechanical factors as the primary source that induces morphological change within the disc. Limitations of the current models, as well as opportunities for future computational modeling work are also discussed.

ActorNode2Vec: An Actor-based solution for Node Embedding over large networks

2020 ◽  
Vol 14 (1) ◽  
pp. 103-114
Author(s):  
Gianfranco Lombardo ◽  
Agostino Poggi
Keyword(s):  
Machine Learning ◽  
Time Complexity ◽  
Language Models ◽  
Machine Learning Techniques ◽  
Large Network ◽  
Actor Model ◽  
Research Fields ◽  
Learning Techniques ◽  
Wide Range ◽  
Distributed Implementation

 The application of Machine Learning techniques over networks, such as prediction tasks over nodes and edges, is becoming often crucial in the analysis of Complex systems in a wide range of research fields. One of the enabling technologies in that sense is represented by Node Embedding, which enables us to learn features automatically over the network. Among the different approaches proposed in the literature, the most promising are DeepWalk and Node2Vec, where the embedding is computed by combining random walks and neural language models. However, characteristic limitations with these techniques are related to memory requirements and time complexity. In this paper, we propose a distributed and scalable solution, named ActorNode2vec, that keeps the best advantages of Node2Vec and overcomes the limitations with the adoption of the actor model to distribute the computational load. We demonstrate the efficacy of this approach with a large network by analyzing the sensitivity of walk length and number of walks parameters and make a comparison also with Deep walk and an Apache Spark distributed implementation of Node2Vec. Results show that with ActorNode2vec computational times are drastically reduced without losing embedding quality and overcoming memory issues.

Efficient Prediction of Structural and Electronic Properties of Hybrid 2D Materials Using DFT and Machine Learning

2018 ◽  
Author(s):  
Sherif Tawfik ◽  
Olexandr Isayev ◽  
Catherine Stampfl ◽  
Joseph Shapter ◽  
David Winkler ◽  
...  
Keyword(s):  
Machine Learning ◽  
Band Gap ◽  
Density Functional ◽  
2D Materials ◽  
Van Der Waals ◽  
Building Blocks ◽  
Machine Learning Techniques ◽  
Interlayer Distance ◽  
Computational Screening ◽  
Wide Range

Materials constructed from different van der Waals two-dimensional (2D) heterostructures offer a wide range of benefits, but these systems have been little studied because of their experimental and computational complextiy, and because of the very large number of possible combinations of 2D building blocks. The simulation of the interface between two different 2D materials is computationally challenging due to the lattice mismatch problem, which sometimes necessitates the creation of very large simulation cells for performing density-functional theory (DFT) calculations. Here we use a combination of DFT, linear regression and machine learning techniques in order to rapidly determine the interlayer distance between two different 2D heterostructures that are stacked in a bilayer heterostructure, as well as the band gap of the bilayer. Our work provides an excellent proof of concept by quickly and accurately predicting a structural property (the interlayer distance) and an electronic property (the band gap) for a large number of hybrid 2D materials. This work paves the way for rapid computational screening of the vast parameter space of van der Waals heterostructures to identify new hybrid materials with useful and interesting properties.

In Silico Assessment of ADME Properties: Advances in Caco-2 Cell Monolayer Permeability Modeling

2019 ◽  
Vol 18 (26) ◽  
pp. 2209-2229 ◽  
Author(s):  
Hai Pham-The ◽  
Miguel Á. Cabrera-Pérez ◽  
Nguyen-Hai Nam ◽  
Juan A. Castillo-Garit ◽  
Bakhtiyor Rasulev ◽  
...  
Keyword(s):  
Intestinal Absorption ◽  
In Silico ◽  
Review Paper ◽  
Cell Monolayer ◽  
Cell Permeability ◽  
Drug Substances ◽  
Wide Range ◽  
Modeling Techniques

One of the main goals of in silico Caco-2 cell permeability models is to identify those drug substances with high intestinal absorption in human (HIA). For more than a decade, several in silico Caco-2 models have been made, applying a wide range of modeling techniques; nevertheless, their capacity for intestinal absorption extrapolation is still doubtful. There are three main problems related to the modest capacity of obtained models, including the existence of inter- and/or intra-laboratory variability of recollected data, the influence of the metabolism mechanism, and the inconsistent in vitro-in vivo correlation (IVIVC) of Caco-2 cell permeability. This review paper intends to sum up the recent advances and limitations of current modeling approaches, and revealed some possible solutions to improve the applicability of in silico Caco-2 permeability models for absorption property profiling, taking into account the above-mentioned issues.

How Scientists Communicate

2020 ◽  
Author(s):  
Alan Kelly
Keyword(s):  
Ethical Issues ◽  
Scientific Communication ◽  
Scientific Publication ◽  
Good Communication ◽  
Wide Range ◽  
Conference Presentations ◽  
Scientific Papers ◽  
History Of ◽  
The Media ◽  
Broad Overview

What is scientific research? It is the process by which we learn about the world. For this research to have an impact, and positively contribute to society, it needs to be communicated to those who need to understand its outcomes and significance for them. Any piece of research is not complete until it has been recorded and passed on to those who need to know about it. So, good communication skills are a key attribute for researchers, and scientists today need to be able to communicate through a wide range of media, from formal scientific papers to presentations and social media, and to a range of audiences, from expert peers to stakeholders to the general public. In this book, the goals and nature of scientific communication are explored, from the history of scientific publication; through the stages of how papers are written, evaluated, and published; to what happens after publication, using examples from landmark historical papers. In addition, ethical issues relating to publication, and the damage caused by cases of fabrication and falsification, are explored. Other forms of scientific communication such as conference presentations are also considered, with a particular focus on presenting and writing for nonspecialist audiences, the media, and other stakeholders. Overall, this book provides a broad overview of the whole range of scientific communication and should be of interest to researchers and also those more broadly interested in the process how what scientists do every day translates into outcomes that contribute to society.

An Overview of Ethics and Environmental Health

2019 ◽  
pp. 697-703
Author(s):  
David B. Resnik
Keyword(s):  
Public Health ◽  
Environmental Health ◽  
Environmental Ethics ◽  
Ethical Issues ◽  
Biomedical Ethics ◽  
Public Health Ethics ◽  
Social Utility ◽  
Toxic Substances ◽  
Health Ethics ◽  
Wide Range

This chapter provides an overview of the ethics of environmental health, and it introduces five chapters in the related section of The Oxford Handbook of Public Health Ethics. A wide range of ethical issues arises in managing the relationship between human health and the environment, including regulation of toxic substances, air and water pollution, waste management, agriculture, the built environment, occupational health, energy production and use, environmental justice, population control, and climate change. The values at stake in environmental health ethics include those usually mentioned in ethical debates in biomedicine and public health, such as autonomy, social utility, and justice, as well as values that address environmental concerns, such as animal welfare, stewardship of biological resources, and sustainability. Environmental health ethics, therefore, stands at the crossroads of several disciplines, including public health ethics, environmental ethics, biomedical ethics, and business ethics.

Occupational hazard in Malaysian traffic police: special focus on air pollutants

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Putri Anis Syahira Mohamad Jamil ◽  
Karmegam Karuppiah ◽  
Irniza Rasdi ◽  
Vivien How ◽  
Shamsul Bahri Mohd Tamrin ◽  
...  
Keyword(s):  
Occupational Injuries ◽  
Indicator System ◽  
Control Measures ◽  
Special Focus ◽  
Safety Measures ◽  
Traffic Police ◽  
Wide Range ◽  
And Control ◽  
Risk Occupation ◽  
High Risk Occupation

Abstract This paper provides a specific deliberation on occupational hazards confronted daily by Malaysian Traffic Police. Traffic police is a high-risk occupation that involves a wide range of tasks and, indirectly, faced with an equally wide variety of hazards at work namely, physical, biological, psychosocial, chemical, and ergonomic hazards. Thereupon, occupational injuries, diseases, and even death are common in the field. The objective of this paper is to collate and explain the major hazards of working as Malaysian traffic police especially in Point Duty Unit, their health effects, and control measures. There are many ways in which these hazards can be minimised by ensuring that sufficient safety measures are taken such as a wireless outdoor individual exposure indicator system for the traffic police. By having this system, air monitoring among traffic police may potentially be easier and accurate. Other methods of mitigating these unfortunate events are incorporated and addressed in this paper according to the duty and needs of traffic police.

scholarly journals Using Satellite Data for CBRN (Chemical, Biological, Radiological, and Nuclear) Threat Detection, Monitoring, and Modelling

2021 ◽  
Author(s):  
Gary Sutlieff ◽  
Lucy Berthoud ◽  
Mark Stinchcombe
Keyword(s):  
Satellite Data ◽  
Meteorological Data ◽  
Atmospheric Composition ◽  
Chemical Detection ◽  
List Type ◽  
Data Types ◽  
Wide Range ◽  
Future Technologies ◽  
The Impact ◽  
Near Future

Abstract CBRN (Chemical, Biological, Radiological, and Nuclear) threats are becoming more prevalent, as more entities gain access to modern weapons and industrial technologies and chemicals. This has produced a need for improvements to modelling, detection, and monitoring of these events. While there are currently no dedicated satellites for CBRN purposes, there are a wide range of possibilities for satellite data to contribute to this field, from atmospheric composition and chemical detection to cloud cover, land mapping, and surface property measurements. This study looks at currently available satellite data, including meteorological data such as wind and cloud profiles, surface properties like temperature and humidity, chemical detection, and sounding. Results of this survey revealed several gaps in the available data, particularly concerning biological and radiological detection. The results also suggest that publicly available satellite data largely does not meet the requirements of spatial resolution, coverage, and latency that CBRN detection requires, outside of providing terrain use and building height data for constructing models. Lastly, the study evaluates upcoming instruments, platforms, and satellite technologies to gauge the impact these developments will have in the near future. Improvements in spatial and temporal resolution as well as latency are already becoming possible, and new instruments will fill in the gaps in detection by imaging a wider range of chemicals and other agents and by collecting new data types. This study shows that with developments coming within the next decade, satellites should begin to provide valuable augmentations to CBRN event detection and monitoring. Article Highlights There is a wide range of existing satellite data in fields that are of interest to CBRN detection and monitoring. The data is mostly of insufficient quality (resolution or latency) for the demanding requirements of CBRN modelling for incident control. Future technologies and platforms will improve resolution and latency, making satellite data more viable in the CBRN management field

scholarly journals Recent Advances in Unmanned Aerial Vehicle Forest Remote Sensing—A Systematic Review. Part I: A General Framework

Forests ◽  
2021 ◽  
Vol 12 (3) ◽  
pp. 327 ◽  
Author(s):  
Riccardo Dainelli ◽  
Piero Toscano ◽  
Salvatore Filippo Di Gennaro ◽  
Alessandro Matese
Keyword(s):  
Remote Sensing ◽  
Unmanned Aerial Vehicle ◽  
Relevant Information ◽  
Forest Monitoring ◽  
Machine Learning Techniques ◽  
Planted Forests ◽  
Systematic Analysis ◽  
Aerial Photogrammetry ◽  
Wide Range ◽  
Aerial Vehicle

Natural, semi-natural, and planted forests are a key asset worldwide, providing a broad range of positive externalities. For sustainable forest planning and management, remote sensing (RS) platforms are rapidly going mainstream. In a framework where scientific production is growing exponentially, a systematic analysis of unmanned aerial vehicle (UAV)-based forestry research papers is of paramount importance to understand trends, overlaps and gaps. The present review is organized into two parts (Part I and Part II). Part II inspects specific technical issues regarding the application of UAV-RS in forestry, together with the pros and cons of different UAV solutions and activities where additional effort is needed, such as the technology transfer. Part I systematically analyzes and discusses general aspects of applying UAV in natural, semi-natural and artificial forestry ecosystems in the recent peer-reviewed literature (2018–mid-2020). The specific goals are threefold: (i) create a carefully selected bibliographic dataset that other researchers can draw on for their scientific works; (ii) analyze general and recent trends in RS forest monitoring (iii) reveal gaps in the general research framework where an additional activity is needed. Through double-step filtering of research items found in the Web of Science search engine, the study gathers and analyzes a comprehensive dataset (226 articles). Papers have been categorized into six main topics, and the relevant information has been subsequently extracted. The strong points emerging from this study concern the wide range of topics in the forestry sector and in particular the retrieval of tree inventory parameters often through Digital Aerial Photogrammetry (DAP), RGB sensors, and machine learning techniques. Nevertheless, challenges still exist regarding the promotion of UAV-RS in specific parts of the world, mostly in the tropical and equatorial forests. Much additional research is required for the full exploitation of hyperspectral sensors and for planning long-term monitoring.

Sign in / Sign up

Export Citation Format

Share Document